Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dictionaries, maps, and JSON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लंबाई
    0.72
    Length
    0.72
     Length
    0.71
     isothermal
    0.69
    length
    0.67
     barbed
    0.67
    logn
    0.66
     length
    0.66
     도입
    0.64
    㖮
    0.64
    POSITIVE LOGITS
     dict
    1.73
     dictionary
    1.73
     dictionaries
    1.58
     Dictionary
    1.57
    Dictionary
    1.56
    字典
    1.53
    dict
    1.51
    NSDictionary
    1.49
     dicion
    1.48
    TimeDict
    1.48
    Act Density 0.514%

    No Known Activations